Revision be14eb619108fa8b7120eb2c42d66d5f623ae10e authored by Brian King on 10 September 2010, 07:03:21 UTC, committed by Jens Axboe on 10 September 2010, 07:03:21 UTC
While testing CPU DLPAR, the following problem was discovered. We were DLPAR removing the first CPU, which in this case was logical CPUs 0-3. CPUs 0-2 were already marked offline and we were in the process of offlining CPU 3. After marking the CPU inactive and offline in cpu_disable, but before the cpu was completely idle (cpu_die), we ended up in __make_request on CPU 3. There we looked at the topology map to see which CPU to complete the I/O on and found no CPUs in the cpu_sibling_map. This resulted in the block layer setting the completion cpu to be NR_CPUS, which then caused an oops when we tried to complete the I/O. Fix this by sanity checking the value we return from blk_cpu_to_group to be a valid cpu value. Signed-off-by: Brian King <brking@linux.vnet.ibm.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
1 parent edce682
| File | Mode | Size |
|---|---|---|
| netfilter | ||
| Kconfig | -rw-r--r-- | 1.6 KB |
| Makefile | -rw-r--r-- | 474 bytes |
| br.c | -rw-r--r-- | 2.2 KB |
| br_device.c | -rw-r--r-- | 7.5 KB |
| br_fdb.c | -rw-r--r-- | 9.7 KB |
| br_forward.c | -rw-r--r-- | 6.1 KB |
| br_if.c | -rw-r--r-- | 10.2 KB |
| br_input.c | -rw-r--r-- | 4.6 KB |
| br_ioctl.c | -rw-r--r-- | 9.2 KB |
| br_multicast.c | -rw-r--r-- | 39.4 KB |
| br_netfilter.c | -rw-r--r-- | 25.9 KB |
| br_netlink.c | -rw-r--r-- | 4.9 KB |
| br_notify.c | -rw-r--r-- | 2.4 KB |
| br_private.h | -rw-r--r-- | 14.6 KB |
| br_private_stp.h | -rw-r--r-- | 1.6 KB |
| br_stp.c | -rw-r--r-- | 10.9 KB |
| br_stp_bpdu.c | -rw-r--r-- | 5.2 KB |
| br_stp_if.c | -rw-r--r-- | 7.0 KB |
| br_stp_timer.c | -rw-r--r-- | 4.4 KB |
| br_sysfs_br.c | -rw-r--r-- | 22.7 KB |
| br_sysfs_if.c | -rw-r--r-- | 7.9 KB |
Computing file changes ...
